Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nobel
    -0.07
     ketogenic
    -0.07
     cube
    -0.07
     आख
    -0.06
     tasted
    -0.06
     tacos
    -0.06
     mas
    -0.06
     Caesar
    -0.06
     began
    -0.06
     connect
    -0.06
    POSITIVE LOGITS
    _candidates
    0.08
     français
    0.07
    栏
    0.07
    SIZE
    0.07
     annoying
    0.06
     SNMP
    0.06
    orWhere
    0.06
    getJSON
    0.06
     haciendo
    0.06
     getModel
    0.06
    Act Density 0.074%

    No Known Activations